Full body motion capture without marker using AI technology
– NEXT-SYSTEM engineer
FUKUOKA CITY, PREFECTURE OF FUKUOKA, JAPAN, January 7, 2022 /EINPresswire.com/ – NEXT-SYSTEM implemented its independently developed AI pose estimation engine “VisionPose” in its “MICHICON-Plus” application, to demonstrate how the AI engine can be used in smartphone applications and tablets.
“MICHICON-Plus” is a real-time full-body motion capture application that captures and reflects motion data on a 3DCG character and supports the export of motion data. It offers a simple way to capture motion without using any equipment other than a smartphone / tablet camera, and can be used for creating VTuber videos and more.
-What is “MICHICON-Plus” and how does it work?
“MICHICON-Plus” is a motion capture application that uses the latest technology to capture a person’s whole body movements using the “VisionPose” AI pose estimation engine, and projects those movements onto a 3DCG character.
When capturing motion, it is usually necessary to prepare several cameras and attach devices such as markers to the target. But with this app, no special equipment or professional camera is needed, as the VisionPose artificial intelligence engine can detect the user’s skeletal information through only the camera of a smartphone or tablet.
It also supports exporting motion data in CSV format and modifying the avatar to other characters through the online platform VRoid Hub *. In addition to real-time motion capture, the app also offers the ability to project the motion of videos on the user’s device onto the 3DCG character. Additionally, AR mode allows the user to make the characters appear as if they are in the real world using camera footage as the background.
* To add characters and export movement data in CSV format, you must upgrade to the PRO version with a monthly subscription (non-renewable subscription, $ 2.99 per month).
Here is a video showing what the app looks like:
–MICHICON Plus video
– Feedback from our engineers
We hope that “MICHICON” will give users the opportunity to familiarize themselves with our AI pose estimation engine, VisionPose. We will continue to develop the application to make it more user-friendly, including the user interface.
-Specifications and system requirements
App name: MICHICON-Plus
Supported operating system: iOS 13.0 and newer models
Application store: MICHICON-PLUS on the App Store (apple.com)
iPhone XS / XS MAX / XR
iPhone 11 ～
iPhone SE (2020)
iPad mini (5th〜) * AR function is not supported
iPad Air (3rd ～) * AR function is not supported
11-inch iPad Pro (1st ～)
12.9-inch iPad Pro (3rd ～)
* Devices with A12 or later processors are recommended.
* Please note that operation on devices not listed above is not covered by warranty or support.
Motion capture analysis
Green screen option
・ Projection of the movements of the videos on the characters (max. 15 seconds)
Camera change (front / rear)
・ CSV output (PRO version only *)
・ Changing characters (PRO version only *)
* PRO version: non-renewable subscription, $ 2.99 per month
-What is VisionPose?
VisionPose is an AI pose estimation engine that detects human skeletal information on real-time camera images, stills and videos, without the need for markers or special equipment. The AI is capable of detecting the skeletal information of 30 key points in 2D and 3D in real time and comes with two out-of-the-box applications in addition to the SDK, so the user can start analyzing immediately after setting up. his PC. As a complete SDK package, it has already been applied to various areas of development and research, and has been implemented by more than 250 customers in Japan. Sales outside of Japan have started with two products, VisionPose Standard for Windows C # and C ++, and the number of supported platforms will also be extended sequentially for Linux / iOS / Jetson.
–VisionPose Promotion Video
-About NEXT-SYSTEM Co., Ltd.
NEXT-SYSTEM is a Japanese systems development company founded in Fukuoka City in 2002, and since then has focused on behavior analysis research through AI technology, development and research of ergonomic systems, the development of advanced systems, such as xR (AR / VR / MR), as well as the development and sale of their pose estimation engine “VisionPose” and their AR signaling system “Kinesys”.
For more information, see the official NEXT-SYSTEM website at:
Whole-body motion capture application powered by “MICHICON-Plus” AI